© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2674
    Prev
    Next
    INDEX
    Explanations

    practice vs reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľ¬èº«çļĦ
    -0.12
    ä¹ł
    -0.09
    èĩªèº«çļĦ
    -0.09
    enan
    -0.09
    æľ¬èº«
    -0.09
    æĢ»çļĦ
    -0.08
    件äºĭ
    -0.08
    åİŁ
    -0.08
    cole
    -0.08
    åĪĿå¿ĥ
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»ä¸Ń
    0.10
    ç»ıéªĮåĴĮ
    0.10
    ä»Ģä¹Īéĥ½
    0.10
    并ä¸įå¤ļ
    0.09
    å¾Īå°ij
    0.09
     Assass
    0.09
    åİ
    0.09
    åıªæľīä¸Ģ个
    0.09
    å¾Īå¤ļæľĭåıĭ
    0.09
    spar
    0.09
    Activations Density 0.055%

    No Known Activations